共查询到20条相似文献,搜索用时 31 毫秒
1.
2.
3.
4.
直觉告诉我们:当人工神经网络算法在多处理器系统上并行实现时,处理器网络的拓扑结构和处理器节点的扇入尺寸(即输入输出规模)会影响并行算法的效率,但是对全连接和随机连接神经网络,上述结论并不成立。在神经网络的并行实现中,处理器的通信开销是一个主要的限制因素,本文将对全连接和随机连接神经网络并行实现的几个相关问题进行讨论。1 学习时间的分解 相似文献
5.
滕明鑫 《数字社区&智能家居》2014,(3):1508-1510
该文运用几种常见数据归一化方法分别对自回归神经网络动态预测模型的预测性能进行分析,结果说明不同数据归一化处理对模型的性能影响非常明显,运用最大运算法进行归一化处理要优于其它几种常见归一化方法。 相似文献
6.
在网络系统优化问题的研究中,目前广泛使用的BP网络模型不能保证收敛到全局最小点,这给网络传输带来误差.为消除网络误差,提高收敛速度,在BP网络加入反馈信号生成内部递归神经网络的误差配准算法.算法在内部递归神经网络引入上次输出的结果,加入先验知识,提高了收敛速度.同时文中对有偏差单元的递归神经网络的误差反向传播学习规则进行了推导,使得网络的累积误差不大于要求值.通过民用航空领域雷达网系统仿真数据仿真表明,算法在消除雷达网系统误差、提高目标精度,对网络系统优化可以取得较好的效果. 相似文献
7.
滕明鑫 《数字社区&智能家居》2014,(7):1508-1510
该文运用几种常见数据归一化方法分别对自回归神经网络动态预测模型的预测性能进行分析,结果说明不同数据归一化处理对模型的性能影响非常明显,运用最大运算法进行归一化处理要优于其它几种常见归一化方法。 相似文献
8.
在许多情况下,弧焊接头的质量用焊缝的几何形状和尺寸来确定.具有给定形状和几何尺寸的焊接接头的获得,实际上就为保证必要的使用性能--强度、塑性和整个焊接构件的疲劳强度作出了保障.同时,无论是直接控制焊接过程,还是预测整个焊接接头质量,都难以正确地评估焊缝成形. 相似文献
9.
探讨了广义回归神经网络的原理和相关算法,将广义回归神经网络应用于赤潮预警,并以米氏凯伦藻为例进行了实验.与目前使用较为广泛的BP神经网络进行比较,结果表明,广义回归神经网络的预警效果要优于BP网络,具有较高的实用价值. 相似文献
10.
高娟 《计算技术与自动化》2008,27(4):24-26
研究一类具有时滞的细胞神经网络的稳定性问题,利用Lyapunov—Krasovskii泛函的方法,给出时滞相关的稳定性判据。稳定性判据是以线性矩阵不等式的形式给出,可以很容易得出时滞的上界。在得到时滞相关的稳定性判据的同时也可以得到时滞无关的稳定性判据。数值算例说明其结果的优越性。 相似文献
11.
12.
针对递归神经网络BP(Back Propagation)学习算法收敛慢的缺陷,提出一种新的递归神经网络快速并行学习算法.首先,引入递推预报误差(RPE)学习算法,并且证明了其稳定性;进一步地,为了克服RPE算法集中运算的不足,设计完整的并行结构算法.本算法将计算分配到神经网络中的每个神经元,完全符合神经网络的并行结构特点,也利于硬件实现.仿真结果表明,该算法比传统的递归BP学习算法具有更好的收敛性能.理论分析和仿真实验证明,该算法与RPE集中运算算法相比可以大大节省计算时间. 相似文献
13.
Jianlin Cheng Michael J. Sweredoski Pierre Baldi 《Data mining and knowledge discovery》2006,13(1):1-10
Protein domains are the structural and functional units of proteins. The ability to parse protein chains into different domains
is important for protein classification and for understanding protein structure, function, and evolution. Here we use machine
learning algorithms, in the form of recursive neural networks, to develop a protein domain predictor called DOMpro. DOMpro
predicts protein domains using a combination of evolutionary information in the form of profiles, predicted secondary structure,
and predicted relative solvent accessibility. DOMpro is trained and tested on a curated dataset derived from the CATH database.
DOMpro correctly predicts the number of domains for 69% of the combined dataset of single and multi-domain chains. DOMpro
achieves a sensitivity of 76% and specificity of 85% with respect to the single-domain proteins and sensitivity of 59% and
specificity of 38% with respect to the two-domain proteins. DOMpro also achieved a sensitivity and specificity of 71% and
71% respectively in the Critical Assessment of Fully Automated Structure Prediction 4 (CAFASP-4) (Fisher et al., 1999; Saini and Fischer, 2005) and was ranked among the top ab initio domain predictors. The DOMpro server, software, and dataset are available at http://www.igb.uci.edu/servers/psss.html. 相似文献
14.
Neural network based adaptive controllers have been shown to achieve much improved accuracy compared with traditional adaptive controllers when applied to trajectory tracking in robot manipulators. This paper describes a new Recursive Prediction Error technique for estimating network parameters which is more computationally efficient. Results show that this neural controller suppresses disturbances accurately and achieves very small errors between commanded and actual trajectories. 相似文献
15.
16.
Intrinsically disordered regions in proteins are relatively frequent and important for our understanding of molecular recognition
and assembly, and protein structure and function. From an algorithmic standpoint, flagging large disordered regions is also
important for ab initio protein structure prediction methods. Here we first extract a curated, non-redundant, data set of protein disordered regions
from the Protein Data Bank and compute relevant statistics on the length and location of these regions. We then develop an
ab initio predictor of disordered regions called DISpro which uses evolutionary information in the form of profiles, predicted secondary
structure and relative solvent accessibility, and ensembles of 1D-recursive neural networks. DISpro is trained and cross validated
using the curated data set. The experimental results show that DISpro achieves an accuracy of 92.8% with a false positive
rate of 5%. DISpro is a member of the SCRATCH suite of protein data mining tools available through 相似文献
17.
In this paper, we point out that the conditions given in [1] are sufficient but unnecessary for the global asymptotically stable equilibrium of a class of delay differential equations. Instead, we prove that under weaker conditions, it is still global asymptotically stable. 相似文献
18.
19.
20.
Vimal Singh 《Neural Processing Letters》2008,27(3):257-265
A modified form of a recent criterion for the global robust stability of interval-delayed Hopfield neural networks is presented. The effectiveness of the modified criterion is demonstrated with the help of an example. 相似文献